Tools
Compare models
Add up to four models via ?models=slug-a,slug-b — or pick from any model page.
| Spec | Anthropic |
|---|---|
| Context | 1M |
| License | |
| Cheapest hosted (out/1M) | $25.00 · Anthropic |
| Released | Jul 24, 2026 |
| LiveBench | 80.08 |
| LiveBench Agentic Coding | 65.2 |
| LiveBench Coding | 81.45 |
| LiveBench Data Analysis | 74.55 |
| LiveBench Instruction Following | 63.77 |
| LiveBench Language | 88.69 |
| LiveBench Mathematics | 95.73 |
| LiveBench Reasoning | 91.21 |
| Arena Agent | 3rd of 55 |
| Arena Agent · Recoverygets back on track after a command fails | 1st of 55 |
| Arena Agent · Steerabilitydoes what it was asked, and changes course when told | 3rd of 55 |
| Arena Agent · Task outcomefinishes what the session set out to do | 5th of 55 |
| Arena Agent · Tool usereaches for the right one, and does not invent one | 25th of 55 |
| Arena Coding | 1533 |
| Arena Creative Writing | 1472 |
| Arena Hard Prompts | 1516 |
| Arena Instruction Following | 1497 |
| Arena Maths | 1523 |
| Arena Text (overall) | 1491 |
| Arena Code (WebDev) | 1693 |
